public static void main(String[] args) {
try {
File myFile = new File("C:\\Users\\wcxjo\\Desktop\\zc\\zc2.txt");//通过字符串创建File类型对象,指向该字符串路径下的文件
List<String> txtList = new ArrayList<>();
if (myFile.isFile() && myFile.exists()) { //判断文件是否存在
InputStreamReader Reader = new InputStreamReader(new FileInputStream(myFile), "UTF-8");
//考虑到编码格式,new FileInputStream(myFile)文件字节输入流,以字节为单位对文件中的数据进行读取
//new InputStreamReader(FileInputStream a, "编码类型")
//将文件字节输入流转换为文件字符输入流并给定编码格式
BufferedReader bufferedReader = new BufferedReader(Reader);
//BufferedReader从字符输入流中读取文本,缓冲各个字符,从而实现字符、数组和行的高效读取。
//通过BuffereReader包装实现高效读取
String lineTxt = null;
while ((lineTxt = bufferedReader.readLine()) != null) {
//buffereReader.readLine()按行读取写成字符串
txtList.add(lineTxt);
System.out.println(lineTxt);
}
Reader.close();
} else {
System.out.println("找不到指定的文件");
}
int a = 0;
Map<String,String> repeat = new HashMap<String,String>();
File f=new File("C:\\Users\\wcxjo\\Desktop\\zc\\zc2222.txt");
FileOutputStream fos1=new FileOutputStream(f);
OutputStreamWriter dos1=new OutputStreamWriter(fos1);
for(String str : txtList){
for(String str2 : txtList){
if(str.equals(str2)){
continue;
}
if(MyUtils.getSimilarityRatio(str,str2) > 80 ){
if(repeat.containsKey(str)|| repeat.containsKey(str2)){
continue;
}
repeat.put(str2,str2);
repeat.put(str,str);
a++;
System.out.println("**********************************************");
System.out.println(str);
System.out.println(str2);
System.out.println("**********************************************");
dos1.write("****************");
dos1.write(System.getProperty("line.separator"));
dos1.write(str);
dos1.write(System.getProperty("line.separator"));
dos1.write(str2);
dos1.write(System.getProperty("line.separator"));
dos1.write("****************");
dos1.write(System.getProperty("line.separator"));
}
}
}
dos1.close();
System.out.println("重复总数:"+a);
} catch (Exception e) {
System.out.println("读取文件内容出错");
e.printStackTrace();
}
}
工具类,字符串重复计算
public class MyUtils {
public static float getSimilarityRatio(String str, String target) {
int d[][]; // 矩阵
int n = str.length();
int m = target.length();
int i; // 遍历str的
int j; // 遍历target的
char ch1; // str的
char ch2; // target的
int temp; // 记录相同字符,在某个矩阵位置值的增量,不是0就是1
if (n == 0 || m == 0) {
return 0;
}
d = new int[n + 1][m + 1];
for (i = 0; i <= n; i++) { // 初始化第一列
d[i][0] = i;
}
for (j = 0; j <= m; j++) { // 初始化第一行
d[0][j] = j;
}
for (i = 1; i <= n; i++) { // 遍历str
ch1 = str.charAt(i - 1);
// 去匹配target
for (j = 1; j <= m; j++) {
ch2 = target.charAt(j - 1);
if (ch1 == ch2 || ch1 == ch2 + 32 || ch1 + 32 == ch2) {
temp = 0;
} else {
temp = 1;
}
// 左边+1,上边+1, 左上角+temp取最小
d[i][j] = Math.min(Math.min(d[i - 1][j] + 1, d[i][j - 1] + 1), d[i - 1][j - 1] + temp);
}
}
return (1 - (float) d[n][m] / Math.max(str.length(), target.length())) * 100F;
}
}